The first AI simulation of a black hole
Abstract
We report the results from our ongoing pilot investigation of the use of deep learning techniques for forecasting the state of turbulent flows onto black holes. Deep neural networks seem to learn well black hole accretion physics and evolve the accretion flow orders of magnitude faster than traditional numerical solvers, while maintaining a reasonable accuracy for a long time.
- Publication:
-
Galaxy Evolution and Feedback across Different Environments
- Pub Date:
- 2021
- DOI:
- 10.1017/S1743921320003981
- arXiv:
- arXiv:2011.12819
- Bibcode:
- 2021IAUS..359..329N
- Keywords:
-
- Black hole physics;
- astrostatistics;
- active galactic nuclei;
- Astrophysics - High Energy Astrophysical Phenomena
- E-Print:
- 5 pages, 2 figures. To be published in Proceedings of IAU Symposium No. 359, 2020, "Galaxy evolution and feedback across different environments". Presented in March 2020